Instructions to use CloveAI/LlamaWeb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CloveAI/LlamaWeb with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "CloveAI/LlamaWeb")

Transformers

How to use CloveAI/LlamaWeb with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="CloveAI/LlamaWeb")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("CloveAI/LlamaWeb", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CloveAI/LlamaWeb with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CloveAI/LlamaWeb"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CloveAI/LlamaWeb",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CloveAI/LlamaWeb

SGLang

How to use CloveAI/LlamaWeb with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "CloveAI/LlamaWeb" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CloveAI/LlamaWeb",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "CloveAI/LlamaWeb" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CloveAI/LlamaWeb",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use CloveAI/LlamaWeb with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for CloveAI/LlamaWeb to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for CloveAI/LlamaWeb to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for CloveAI/LlamaWeb to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="CloveAI/LlamaWeb",
    max_seq_length=2048,
)

Docker Model Runner
How to use CloveAI/LlamaWeb with Docker Model Runner:
```
docker model run hf.co/CloveAI/LlamaWeb
```

Alan Joshua commited on Nov 7, 2025

Commit

b1d5e52

verified ·

1 Parent(s): 73af346

Upload folder using huggingface_hub

Browse files

Files changed (5) hide show

README.md +2 -48
adapter_config.json +5 -5
adapter_model.safetensors +2 -2
tokenizer_config.json +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -1,9 +1,9 @@
 ---
-base_model: unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit
 library_name: peft
 pipeline_tag: text-generation
 tags:
-- base_model:adapter:unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit
 - lora
 - sft
 - transformers
@@ -11,52 +11,6 @@ tags:
 - unsloth
 ---
-```python
-import torch
-from unsloth import FastLanguageModel
-# Load your LoRA fine-tuned model
-model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name = "alanjoshua2005/LlamaWeb",  # path to your fine-tuned model
-    max_seq_length = 2048,
-    dtype = None,  # Auto-detect precision
-    load_in_4bit = True,  # or False if you're on CPU
-)
-#test_prompt = "Create a modern hero section for a travel booking website using Tailwind CSS."
-test_prompt = """You are an expert Tailwind CSS web designer.
-Generate a **complete stunning HTML5 landing page** wrapped in <html>, <head>, and <body> tags.
-Do NOT stop until the full closing </html> tag is produced.
-Title: "Amazing Places to Visit"
-Requirements:
-- Include navigation bar, hero section, features section, pricing section, and footer.
-- Use TailwindCSS via CDN.
-- Use modern, responsive design and aesthetic color schemes.
-Output only the HTML code, nothing else."""
-inputs = tokenizer(test_prompt, return_tensors="pt").to(model.device)
-# Generate
-with torch.no_grad():
-    outputs = model.generate(
-        **inputs,
-        max_new_tokens=2000,
-        temperature=0.6,
-        top_p=0.9,
-        do_sample=True,
-        repetition_penalty=1.15,
-        eos_token_id=tokenizer.eos_token_id,
-    )
-# Decode output
-generated_html = tokenizer.decode(outputs[0], skip_special_tokens=True)
-print(generated_html)
-```
 # Model Card for Model ID
 <!-- Provide a quick summary of what the model is/does. -->

 ---
+base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
 library_name: peft
 pipeline_tag: text-generation
 tags:
+- base_model:adapter:unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
 - lora
 - sft
 - transformers
 - unsloth
 ---
 # Model Card for Model ID
 <!-- Provide a quick summary of what the model is/does. -->

adapter_config.json CHANGED Viewed

@@ -5,7 +5,7 @@
     "parent_library": "transformers.models.llama.modeling_llama",
     "unsloth_fixed": true
   },
-  "base_model_name_or_path": "unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "v_proj",
     "o_proj",
     "up_proj",
     "k_proj",
-    "down_proj",
-    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

     "parent_library": "transformers.models.llama.modeling_llama",
     "unsloth_fixed": true
   },
+  "base_model_name_or_path": "unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "o_proj",
+    "down_proj",
+    "q_proj",
     "up_proj",
+    "gate_proj",
     "k_proj",
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5022073a383f8db1c3a32b9bc61fb3afd0d13202728b8ac66c0a7d6c090deb8
-size 45118424

 version https://git-lfs.github.com/spec/v1
+oid sha256:88ea72cf5ae98dfd7506a596599bb0961e844df66a0f4097497716b34f0ff8e7
+size 97307544

tokenizer_config.json CHANGED Viewed

@@ -2060,7 +2060,7 @@
   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
-  "padding_side": "right",
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": null
 }

   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": null
 }

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8b63f3de20fe31fb778bf092280655ac0350977f2a49c3bf46fe1c2c3e7c539
 size 6289

 version https://git-lfs.github.com/spec/v1
+oid sha256:8c77f48404575c98b26c8b3ee04032fef86c86a85befbe1b7d46da6a625494bd
 size 6289